Merge branch 'next' into for-linus

Prepare input updates for 5.14 merge window.

54 files changed, 623 insertions, 171 deletions

diff --git a/tools/arch/ia64/include/asm/barrier.h b/tools/arch/ia64/include/asm/barrier.h
index 4d471d9511a5..6fffe5682713 100644
--- a/tools/arch/ia64/include/asm/barrier.h
+++ b/tools/arch/ia64/include/asm/barrier.h
@@ -39,9 +39,6 @@
  * sequential memory pages only.
  */
 
-/* XXX From arch/ia64/include/uapi/asm/gcc_intrin.h */
-#define ia64_mf()       asm volatile ("mf" ::: "memory")
-
 #define mb()		ia64_mf()
 #define rmb()		mb()
 #define wmb()		mb()
diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py
index c4225ed63565..1600b17dbb8a 100644
--- a/tools/cgroup/memcg_slabinfo.py
+++ b/tools/cgroup/memcg_slabinfo.py
@@ -128,9 +128,9 @@ def detect_kernel_config():
 
     cfg['nr_nodes'] = prog['nr_online_nodes'].value_()
 
-    if prog.type('struct kmem_cache').members[1][1] == 'flags':
+    if prog.type('struct kmem_cache').members[1].name == 'flags':
         cfg['allocator'] = 'SLUB'
-    elif prog.type('struct kmem_cache').members[1][1] == 'batchcount':
+    elif prog.type('struct kmem_cache').members[1].name == 'batchcount':
         cfg['allocator'] = 'SLAB'
     else:
         err('Can\'t determine the slab allocator')
@@ -193,7 +193,7 @@ def main():
         # look over all slab pages, belonging to non-root memcgs
         # and look for objects belonging to the given memory cgroup
         for page in for_each_slab_page(prog):
-            objcg_vec_raw = page.obj_cgroups.value_()
+            objcg_vec_raw = page.memcg_data.value_()
             if objcg_vec_raw == 0:
                 continue
             cache = page.slab_cache
@@ -202,7 +202,7 @@ def main():
             addr = cache.value_()
             caches[addr] = cache
             # clear the lowest bit to get the true obj_cgroups
-            objcg_vec = Object(prog, page.obj_cgroups.type_,
+            objcg_vec = Object(prog, 'struct obj_cgroup **',
                                value=objcg_vec_raw & ~1)
 
             if addr not in stats:
diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h
index 637189ec1ab9..d30439b4b8ab 100644
--- a/tools/include/uapi/asm/errno.h
+++ b/tools/include/uapi/asm/errno.h
@@ -9,8 +9,6 @@
 #include "../../../arch/alpha/include/uapi/asm/errno.h"
 #elif defined(__mips__)
 #include "../../../arch/mips/include/uapi/asm/errno.h"
-#elif defined(__ia64__)
-#include "../../../arch/ia64/include/uapi/asm/errno.h"
 #elif defined(__xtensa__)
 #include "../../../arch/xtensa/include/uapi/asm/errno.h"
 #else
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 8b281f722e5b..f6afee209620 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1154,6 +1154,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR	(1 << 0)
 #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
 #define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1621,12 +1622,24 @@ struct kvm_xen_vcpu_attr {
 	union {
 		__u64 gpa;
 		__u64 pad[8];
+		struct {
+			__u64 state;
+			__u64 state_entry_time;
+			__u64 time_running;
+			__u64 time_runnable;
+			__u64 time_blocked;
+			__u64 time_offline;
+		} runstate;
 	} u;
 };
 
 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO	0x0
 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO	0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR	0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT	0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA	0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST	0x5
 
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
diff --git a/tools/kvm/kvm_stat/kvm_stat.service b/tools/kvm/kvm_stat/kvm_stat.service
index 71aabaffe779..8f13b843d5b4 100644
--- a/tools/kvm/kvm_stat/kvm_stat.service
+++ b/tools/kvm/kvm_stat/kvm_stat.service
@@ -9,6 +9,7 @@ Type=simple
 ExecStart=/usr/bin/kvm_stat -dtcz -s 10 -L /var/log/kvm_stat.csv
 ExecReload=/bin/kill -HUP $MAINPID
 Restart=always
+RestartSec=60s
 SyslogIdentifier=kvm_stat
 SyslogLevel=debug
 
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 887a494ad5fc..e9eb6a6e80d2 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -215,7 +215,7 @@ define do_install
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
 	fi;						\
-	$(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2'
+	$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
 endef
 
 install_lib: all_cmd
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 2f9d685bd522..0911aea4cdbe 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -462,7 +462,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 		return err;
 
 	case BTF_KIND_ARRAY:
-		return btf_dump_order_type(d, btf_array(t)->type, through_ptr);
+		return btf_dump_order_type(d, btf_array(t)->type, false);
 
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION: {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d43cc3f29dae..4181d178ee7b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1181,7 +1181,8 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) {
 		pr_warn("elf: failed to get section names strings from %s: %s\n",
 			obj->path, elf_errmsg(-1));
-		return -LIBBPF_ERRNO__FORMAT;
+		err = -LIBBPF_ERRNO__FORMAT;
+		goto errout;
 	}
 
 	/* Old LLVM set e_machine to EM_NONE */
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 4dd73de00b6f..d2cb28e9ef52 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -40,7 +40,7 @@ static int libbpf_netlink_open(__u32 *nl_pid)
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
 
-	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE);
 	if (sock < 0)
 		return -errno;
 
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 8caaafe7e312..e7a8d847161f 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -227,7 +227,7 @@ static int ringbuf_process_ring(struct ring* r)
 			if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) {
 				sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ;
 				err = r->sample_cb(r->ctx, sample, len);
-				if (err) {
+				if (err < 0) {
 					/* update consumer pos and bail out */
 					smp_store_release(r->consumer_pos,
 							  cons_pos);
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 526fc35c0b23..007fe5d59438 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -59,6 +59,8 @@ struct xsk_umem {
 	int fd;
 	int refcount;
 	struct list_head ctx_list;
+	bool rx_ring_setup_done;
+	bool tx_ring_setup_done;
 };
 
 struct xsk_ctx {
@@ -743,26 +745,30 @@ static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex,
 	return NULL;
 }
 
-static void xsk_put_ctx(struct xsk_ctx *ctx)
+static void xsk_put_ctx(struct xsk_ctx *ctx, bool unmap)
 {
 	struct xsk_umem *umem = ctx->umem;
 	struct xdp_mmap_offsets off;
 	int err;
 
-	if (--ctx->refcount == 0) {
-		err = xsk_get_mmap_offsets(umem->fd, &off);
-		if (!err) {
-			munmap(ctx->fill->ring - off.fr.desc,
-			       off.fr.desc + umem->config.fill_size *
-			       sizeof(__u64));
-			munmap(ctx->comp->ring - off.cr.desc,
-			       off.cr.desc + umem->config.comp_size *
-			       sizeof(__u64));
-		}
+	if (--ctx->refcount)
+		return;
 
-		list_del(&ctx->list);
-		free(ctx);
-	}
+	if (!unmap)
+		goto out_free;
+
+	err = xsk_get_mmap_offsets(umem->fd, &off);
+	if (err)
+		goto out_free;
+
+	munmap(ctx->fill->ring - off.fr.desc, off.fr.desc + umem->config.fill_size *
+	       sizeof(__u64));
+	munmap(ctx->comp->ring - off.cr.desc, off.cr.desc + umem->config.comp_size *
+	       sizeof(__u64));
+
+out_free:
+	list_del(&ctx->list);
+	free(ctx);
 }
 
 static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
@@ -797,8 +803,6 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 	memcpy(ctx->ifname, ifname, IFNAMSIZ - 1);
 	ctx->ifname[IFNAMSIZ - 1] = '\0';
 
-	umem->fill_save = NULL;
-	umem->comp_save = NULL;
 	ctx->fill = fill;
 	ctx->comp = comp;
 	list_add(&ctx->list, &umem->ctx_list);
@@ -848,6 +852,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 			      struct xsk_ring_cons *comp,
 			      const struct xsk_socket_config *usr_config)
 {
+	bool unmap, rx_setup_done = false, tx_setup_done = false;
 	void *rx_map = NULL, *tx_map = NULL;
 	struct sockaddr_xdp sxdp = {};
 	struct xdp_mmap_offsets off;
@@ -858,6 +863,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	if (!umem || !xsk_ptr || !(rx || tx))
 		return -EFAULT;
 
+	unmap = umem->fill_save != fill;
+
 	xsk = calloc(1, sizeof(*xsk));
 	if (!xsk)
 		return -ENOMEM;
@@ -881,6 +888,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 		}
 	} else {
 		xsk->fd = umem->fd;
+		rx_setup_done = umem->rx_ring_setup_done;
+		tx_setup_done = umem->tx_ring_setup_done;
 	}
 
 	ctx = xsk_get_ctx(umem, ifindex, queue_id);
@@ -899,7 +908,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	}
 	xsk->ctx = ctx;
 
-	if (rx) {
+	if (rx && !rx_setup_done) {
 		err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
 				 &xsk->config.rx_size,
 				 sizeof(xsk->config.rx_size));
@@ -907,8 +916,10 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 			err = -errno;
 			goto out_put_ctx;
 		}
+		if (xsk->fd == umem->fd)
+			umem->rx_ring_setup_done = true;
 	}
-	if (tx) {
+	if (tx && !tx_setup_done) {
 		err = setsockopt(xsk->fd, SOL_XDP, XDP_TX_RING,
 				 &xsk->config.tx_size,
 				 sizeof(xsk->config.tx_size));
@@ -916,6 +927,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 			err = -errno;
 			goto out_put_ctx;
 		}
+		if (xsk->fd == umem->fd)
+			umem->rx_ring_setup_done = true;
 	}
 
 	err = xsk_get_mmap_offsets(xsk->fd, &off);
@@ -994,6 +1007,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	}
 
 	*xsk_ptr = xsk;
+	umem->fill_save = NULL;
+	umem->comp_save = NULL;
 	return 0;
 
 out_mmap_tx:
@@ -1005,7 +1020,7 @@ out_mmap_rx:
 		munmap(rx_map, off.rx.desc +
 		       xsk->config.rx_size * sizeof(struct xdp_desc));
 out_put_ctx:
-	xsk_put_ctx(ctx);
+	xsk_put_ctx(ctx, unmap);
 out_socket:
 	if (--umem->refcount)
 		close(xsk->fd);
@@ -1019,6 +1034,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		       struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
 		       const struct xsk_socket_config *usr_config)
 {
+	if (!umem)
+		return -EFAULT;
+
 	return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem,
 					 rx, tx, umem->fill_save,
 					 umem->comp_save, usr_config);
@@ -1068,7 +1086,7 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 		}
 	}
 
-	xsk_put_ctx(ctx);
+	xsk_put_ctx(ctx, true);
 
 	umem->refcount--;
 	/* Do not close an fd that also has an associated umem connected
diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index ace8772a4f03..7c4a9d424a64 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -402,35 +402,42 @@ static pid_t handle_signalfd(struct daemon *daemon)
 	int status;
 	pid_t pid;
 
+	/*
+	 * Take signal fd data as pure signal notification and check all
+	 * the sessions state. The reason is that multiple signals can get
+	 * coalesced in kernel and we can receive only single signal even
+	 * if multiple SIGCHLD were generated.
+	 */
 	err = read(daemon->signal_fd, &si, sizeof(struct signalfd_siginfo));
-	if (err != sizeof(struct signalfd_siginfo))
+	if (err != sizeof(struct signalfd_siginfo)) {
+		pr_err("failed to read signal fd\n");
 		return -1;
+	}
 
 	list_for_each_entry(session, &daemon->sessions, list) {
+		if (session->pid == -1)
+			continue;
 
-		if (session->pid != (int) si.ssi_pid)
+		pid = waitpid(session->pid, &status, WNOHANG);
+		if (pid <= 0)
 			continue;
 
-		pid = waitpid(session->pid, &status, 0);
-		if (pid == session->pid) {
-			if (WIFEXITED(status)) {
-				pr_info("session '%s' exited, status=%d\n",
-					session->name, WEXITSTATUS(status));
-			} else if (WIFSIGNALED(status)) {
-				pr_info("session '%s' killed (signal %d)\n",
-					session->name, WTERMSIG(status));
-			} else if (WIFSTOPPED(status)) {
-				pr_info("session '%s' stopped (signal %d)\n",
-					session->name, WSTOPSIG(status));
-			} else {
-				pr_info("session '%s' Unexpected status (0x%x)\n",
-					session->name, status);
-			}
+		if (WIFEXITED(status)) {
+			pr_info("session '%s' exited, status=%d\n",
+				session->name, WEXITSTATUS(status));
+		} else if (WIFSIGNALED(status)) {
+			pr_info("session '%s' killed (signal %d)\n",
+				session->name, WTERMSIG(status));
+		} else if (WIFSTOPPED(status)) {
+			pr_info("session '%s' stopped (signal %d)\n",
+				session->name, WSTOPSIG(status));
+		} else {
+			pr_info("session '%s' Unexpected status (0x%x)\n",
+				session->name, status);
 		}
 
 		session->state = KILL;
 		session->pid = -1;
-		return pid;
 	}
 
 	return 0;
@@ -443,7 +450,6 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
 		.fd	= daemon->signal_fd,
 		.events	= POLLIN,
 	};
-	pid_t wpid = 0, pid = session->pid;
 	time_t start;
 
 	start = time(NULL);
@@ -452,7 +458,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
 		int err = poll(&pollfd, 1, 1000);
 
 		if (err > 0) {
-			wpid = handle_signalfd(daemon);
+			handle_signalfd(daemon);
 		} else if (err < 0) {
 			perror("failed: poll\n");
 			return -1;
@@ -460,7 +466,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
 
 		if (start + secs < time(NULL))
 			return -1;
-	} while (wpid != pid);
+	} while (session->pid != -1);
 
 	return 0;
 }
@@ -902,7 +908,9 @@ static void daemon_session__kill(struct daemon_session *session,
 			daemon_session__signal(session, SIGKILL);
 			break;
 		default:
-			break;
+			pr_err("failed to wait for session %s\n",
+			       session->name);
+			return;
 		}
 		how++;
 
@@ -955,7 +963,8 @@ static void daemon__kill(struct daemon *daemon)
 			daemon__signal(daemon, SIGKILL);
 			break;
 		default:
-			break;
+			pr_err("failed to wait for sessions\n");
+			return;
 		}
 		how++;
 
@@ -1344,7 +1353,7 @@ out:
 		close(sock_fd);
 	if (conf_fd != -1)
 		close(conf_fd);
-	if (conf_fd != -1)
+	if (signal_fd != -1)
 		close(signal_fd);
 
 	pr_info("daemon exited\n");
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index d49448a1060c..87cb11a7a3ee 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -289,7 +289,7 @@ static int set_tracing_pid(struct perf_ftrace *ftrace)
 
 	for (i = 0; i < perf_thread_map__nr(ftrace->evlist->core.threads); i++) {
 		scnprintf(buf, sizeof(buf), "%d",
-			  ftrace->evlist->core.threads->map[i]);
+			  perf_thread_map__pid(ftrace->evlist->core.threads, i));
 		if (append_tracing_file("set_ftrace_pid", buf) < 0)
 			return -1;
 	}
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 6fe44d97fde5..ddccc0eb7390 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -906,7 +906,7 @@ int cmd_inject(int argc, const char **argv)
 	}
 
 	data.path = inject.input_name;
-	inject.session = perf_session__new(&data, true, &inject.tool);
+	inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool);
 	if (IS_ERR(inject.session))
 		return PTR_ERR(inject.session);
 
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index f57e075b0ed2..c72adbd67386 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -86,7 +86,7 @@ static struct {
 		.msg_load_fail	  = "check your vmlinux setting?",
 		.target_func	  = &epoll_pwait_loop,
 		.expect_result	  = (NR_ITERS + 1) / 2,
-		.pin 		  = true,
+		.pin		  = true,
 	},
 #ifdef HAVE_BPF_PROLOGUE
 	{
@@ -99,13 +99,6 @@ static struct {
 		.expect_result	  = (NR_ITERS + 1) / 4,
 	},
 #endif
-	{
-		.prog_id	  = LLVM_TESTCASE_BPF_RELOCATION,
-		.desc		  = "BPF relocation checker",
-		.name		  = "[bpf_relocation_test]",
-		.msg_compile_fail = "fix 'perf test LLVM' first",
-		.msg_load_fail	  = "libbpf error when dealing with relocation",
-	},
 };
 
 static int do_test(struct bpf_object *obj, int (*func)(void),
diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
index 5ad3ca8d681b..58984380b211 100755
--- a/tools/perf/tests/shell/daemon.sh
+++ b/tools/perf/tests/shell/daemon.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # daemon operations
 # SPDX-License-Identifier: GPL-2.0
 
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
index f3ac9d40cebf..2e5eff4f8f03 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
@@ -210,8 +210,10 @@ static int arm_spe_do_get_packet(const unsigned char *buf, size_t len,
 
 	if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_EXTENDED) {
 		/* 16-bit extended format header */
-		ext_hdr = 1;
+		if (len == 1)
+			return ARM_SPE_BAD_PACKET;
 
+		ext_hdr = 1;
 		hdr = buf[1];
 		if (hdr == SPE_HEADER1_ALIGNMENT)
 			return arm_spe_get_alignment(buf, len, packet);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 953f4afacd3b..1b4091a3b508 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -298,10 +298,6 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
 		queue->set = true;
 		queue->tid = buffer->tid;
 		queue->cpu = buffer->cpu;
-	} else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
-		pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
-		       queue->cpu, queue->tid, buffer->cpu, buffer->tid);
-		return -EINVAL;
 	}
 
 	buffer->buffer_nr = queues->next_buffer_nr++;
@@ -638,7 +634,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 		break;
 	}
 
-	if (itr)
+	if (itr && itr->parse_snapshot_options)
 		return itr->parse_snapshot_options(itr, opts, str);
 
 	pr_err("No AUX area tracing to snapshot\n");
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index 423ec69bda6c..5ecd4f401f32 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -201,7 +201,7 @@ static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt,
 	double ratio = 0.0;
 
 	if (block_fmt->total_cycles)
-		ratio = (double)bi->cycles / (double)block_fmt->total_cycles;
+		ratio = (double)bi->cycles_aggr / (double)block_fmt->total_cycles;
 
 	return color_pct(hpp, block_fmt->width, 100.0 * ratio);
 }
@@ -216,9 +216,9 @@ static int64_t block_total_cycles_pct_sort(struct perf_hpp_fmt *fmt,
 	double l, r;
 
 	if (block_fmt->total_cycles) {
-		l = ((double)bi_l->cycles /
+		l = ((double)bi_l->cycles_aggr /
 			(double)block_fmt->total_cycles) * 100000.0;
-		r = ((double)bi_r->cycles /
+		r = ((double)bi_r->cycles_aggr /
 			(double)block_fmt->total_cycles) * 100000.0;
 		return (int64_t)l - (int64_t)r;
 	}
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 57d58c81a5f8..cdecda1ddd36 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -196,25 +196,32 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
 	}
 
 	if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+		free(info_linear);
 		pr_debug("%s: the kernel is too old, aborting\n", __func__);
 		return -2;
 	}
 
 	info = &info_linear->info;
+	if (!info->jited_ksyms) {
+		free(info_linear);
+		return -1;
+	}
 
 	/* number of ksyms, func_lengths, and tags should match */
 	sub_prog_cnt = info->nr_jited_ksyms;
 	if (sub_prog_cnt != info->nr_prog_tags ||
-	    sub_prog_cnt != info->nr_jited_func_lens)
+	    sub_prog_cnt != info->nr_jited_func_lens) {
+		free(info_linear);
 		return -1;
+	}
 
 	/* check BTF func info support */
 	if (info->btf_id && info->nr_func_info && info->func_info_rec_size) {
 		/* btf func info number should be same as sub_prog_cnt */
 		if (sub_prog_cnt != info->nr_func_info) {
 			pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
-			err = -1;
-			goto out;
+			free(info_linear);
+			return -1;
 		}
 		if (btf__get_from_id(info->btf_id, &btf)) {
 			pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id);
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index f29af4fc3d09..8fca4779ae6a 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -35,7 +35,7 @@ void perf_data__close_dir(struct perf_data *data)
 int perf_data__create_dir(struct perf_data *data, int nr)
 {
 	struct perf_data_file *files = NULL;
-	int i, ret = -1;
+	int i, ret;
 
 	if (WARN_ON(!data->is_dir))
 		return -EINVAL;
@@ -51,7 +51,8 @@ int perf_data__create_dir(struct perf_data *data, int nr)
 	for (i = 0; i < nr; i++) {
 		struct perf_data_file *file = &files[i];
 
-		if (asprintf(&file->path, "%s/data.%d", data->path, i) < 0)
+		ret = asprintf(&file->path, "%s/data.%d", data->path, i);
+		if (ret < 0)
 			goto out_err;
 
 		ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index fbc40a2c17d4..8af693d9678c 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -840,15 +840,18 @@ out:
 int maps__clone(struct thread *thread, struct maps *parent)
 {
 	struct maps *maps = thread->maps;
-	int err = -ENOMEM;
+	int err;
 	struct map *map;
 
 	down_read(&parent->lock);
 
 	maps__for_each_entry(parent, map) {
 		struct map *new = map__clone(map);
-		if (new == NULL)
+
+		if (new == NULL) {
+			err = -ENOMEM;
 			goto out_unlock;
+		}
 
 		err = unwind__prepare_access(maps, new, NULL);
 		if (err)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 42c84adeb2fb..c0c0fab22cb8 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -356,6 +356,9 @@ __add_event(struct list_head *list, int *idx,
 	struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
 			       cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
 
+	if (pmu && attr->type == PERF_TYPE_RAW)
+		perf_pmu__warn_invalid_config(pmu, attr->config, name);
+
 	if (init_attr)
 		event_attr_init(attr);
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 44ef28302fc7..46fd0f998484 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1812,3 +1812,36 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu)
 
 	return nr_caps;
 }
+
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+				   char *name)
+{
+	struct perf_pmu_format *format;
+	__u64 masks = 0, bits;
+	char buf[100];
+	unsigned int i;
+
+	list_for_each_entry(format, &pmu->format, list)	{
+		if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG)
+			continue;
+
+		for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS)
+			masks |= 1ULL << i;
+	}
+
+	/*
+	 * Kernel doesn't export any valid format bits.
+	 */
+	if (masks == 0)
+		return;
+
+	bits = config & ~masks;
+	if (bits == 0)
+		return;
+
+	bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf));
+
+	pr_warning("WARNING: event '%s' not valid (bits %s of config "
+		   "'%llx' not supported by kernel)!\n",
+		   name ?: "N/A", buf, config);
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 8164388478c6..160b0f561771 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -123,4 +123,7 @@ int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
 int perf_pmu__caps_parse(struct perf_pmu *pmu);
 
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+				   char *name);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index b698046ec2db..dff178103ce5 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -424,7 +424,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 
 	while (!io.eof) {
 		static const char anonstr[] = "//anon";
-		size_t size;
+		size_t size, aligned_size;
 
 		/* ensure null termination since stack will be reused. */
 		event->mmap2.filename[0] = '\0';
@@ -484,11 +484,12 @@ out:
 		}
 
 		size = strlen(event->mmap2.filename) + 1;
-		size = PERF_ALIGN(size, sizeof(u64));
+		aligned_size = PERF_ALIGN(size, sizeof(u64));
 		event->mmap2.len -= event->mmap.start;
 		event->mmap2.header.size = (sizeof(event->mmap2) -
-					(sizeof(event->mmap2.filename) - size));
-		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+					(sizeof(event->mmap2.filename) - aligned_size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size +
+			(aligned_size - size));
 		event->mmap2.header.size += machine->id_hdr_size;
 		event->mmap2.pid = tgid;
 		event->mmap2.tid = pid;
@@ -758,7 +759,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 	for (i = 0; i < n; i++) {
 		char *end;
 		pid_t _pid;
-		bool kernel_thread;
+		bool kernel_thread = false;
 
 		_pid = strtol(dirent[i]->d_name, &end, 10);
 		if (*end)
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 3cc91ad048ea..43beb169631d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -133,6 +133,8 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	if (dso != NULL) {
 		__dsos__add(&machine->dsos, dso);
 		dso__set_long_name(dso, long_name, false);
+		/* Put dso here because __dsos_add already got it */
+		dso__put(dso);
 	}
 
 	return dso;
diff --git a/tools/testing/kunit/configs/broken_on_uml.config b/tools/testing/kunit/configs/broken_on_uml.config
index a7f0603d33f6..690870043ac0 100644
--- a/tools/testing/kunit/configs/broken_on_uml.config
+++ b/tools/testing/kunit/configs/broken_on_uml.config
@@ -40,3 +40,5 @@
 # CONFIG_RESET_BRCMSTB_RESCAL is not set
 # CONFIG_RESET_INTEL_GW is not set
 # CONFIG_ADI_AXI_ADC is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_PAGE_POISONING is not set
diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py
index 0b550cbd667d..1e2683dcc0e7 100644
--- a/tools/testing/kunit/kunit_config.py
+++ b/tools/testing/kunit/kunit_config.py
@@ -13,7 +13,7 @@ from typing import List, Set
 CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_(\w+) is not set$'
 CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+|".*")$'
 
-KconfigEntryBase = collections.namedtuple('KconfigEntry', ['name', 'value'])
+KconfigEntryBase = collections.namedtuple('KconfigEntryBase', ['name', 'value'])
 
 class KconfigEntry(KconfigEntryBase):
 
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 3b796dd5e577..ca24f6839d50 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -296,21 +296,34 @@ static void *idr_throbber(void *arg)
 	return NULL;
 }
 
+/*
+ * There are always either 1 or 2 objects in the IDR.  If we find nothing,
+ * or we find something at an ID we didn't expect, that's a bug.
+ */
 void idr_find_test_1(int anchor_id, int throbber_id)
 {
 	pthread_t throbber;
 	time_t start = time(NULL);
 
-	pthread_create(&throbber, NULL, idr_throbber, &throbber_id);
-
 	BUG_ON(idr_alloc(&find_idr, xa_mk_value(anchor_id), anchor_id,
 				anchor_id + 1, GFP_KERNEL) != anchor_id);
 
+	pthread_create(&throbber, NULL, idr_throbber, &throbber_id);
+
+	rcu_read_lock();
 	do {
 		int id = 0;
 		void *entry = idr_get_next(&find_idr, &id);
-		BUG_ON(entry != xa_mk_value(id));
+		rcu_read_unlock();
+		if ((id != anchor_id && id != throbber_id) ||
+		    entry != xa_mk_value(id)) {
+			printf("%s(%d, %d): %p at %d\n", __func__, anchor_id,
+				throbber_id, entry, id);
+			abort();
+		}
+		rcu_read_lock();
 	} while (time(NULL) < start + 11);
+	rcu_read_unlock();
 
 	pthread_join(throbber, NULL);
 
@@ -577,6 +590,7 @@ void ida_tests(void)
 
 int __weak main(void)
 {
+	rcu_register_thread();
 	radix_tree_init();
 	idr_checks();
 	ida_tests();
@@ -584,5 +598,6 @@ int __weak main(void)
 	rcu_barrier();
 	if (nr_allocated)
 		printf("nr_allocated = %d\n", nr_allocated);
+	rcu_unregister_thread();
 	return 0;
 }
diff --git a/tools/testing/radix-tree/linux/compiler_types.h b/tools/testing/radix-tree/linux/compiler_types.h
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/tools/testing/radix-tree/linux/compiler_types.h
+++ /dev/null
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 9eae0fb5a67d..e00520cc6349 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -224,7 +224,9 @@ void multiorder_checks(void)
 
 int __weak main(void)
 {
+	rcu_register_thread();
 	radix_tree_init();
 	multiorder_checks();
+	rcu_unregister_thread();
 	return 0;
 }
diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c
index e61e43efe463..f20e12cbbfd4 100644
--- a/tools/testing/radix-tree/xarray.c
+++ b/tools/testing/radix-tree/xarray.c
@@ -25,11 +25,13 @@ void xarray_tests(void)
 
 int __weak main(void)
 {
+	rcu_register_thread();
 	radix_tree_init();
 	xarray_tests();
 	radix_tree_cpu_dead(1);
 	rcu_barrier();
 	if (nr_allocated)
 		printf("nr_allocated = %d\n", nr_allocated);
+	rcu_unregister_thread();
 	return 0;
 }
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 9210691aa998..e3e08d9c7020 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -284,16 +284,28 @@ endfunction
 // Set up test pattern in the FFR
 // x0: pid
 // x2: generation
+//
+// We need to generate a canonical FFR value, which consists of a number of
+// low "1" bits, followed by a number of zeros. This gives us 17 unique values
+// per 16 bits of FFR, so we create a 4 bit signature out of the PID and
+// generation, and use that as the initial number of ones in the pattern.
+// We fill the upper lanes of FFR with zeros.
 // Beware: corrupts P0.
 function setup_ffr
 	mov	x4, x30
 
-	bl	pattern
+	and	w0, w0, #0x3
+	bfi	w0, w2, #2, #2
+	mov	w1, #1
+	lsl	w1, w1, w0
+	sub	w1, w1, #1
+
 	ldr	x0, =ffrref
-	ldr	x1, =scratch
-	rdvl	x2, #1
-	lsr	x2, x2, #3
-	bl	memcpy
+	strh	w1, [x0], 2
+	rdvl	x1, #1
+	lsr	x1, x1, #3
+	sub	x1, x1, #2
+	bl	memclr
 
 	mov	x0, #0
 	ldr	x1, =ffrref
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 37c5494a0381..e25917f04602 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -6,6 +6,7 @@
 #include <test_progs.h>
 #include "bpf_dctcp.skel.h"
 #include "bpf_cubic.skel.h"
+#include "bpf_tcp_nogpl.skel.h"
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
 
@@ -227,10 +228,53 @@ static void test_dctcp(void)
 	bpf_dctcp__destroy(dctcp_skel);
 }
 
+static char *err_str;
+static bool found;
+
+static int libbpf_debug_print(enum libbpf_print_level level,
+			      const char *format, va_list args)
+{
+	char *log_buf;
+
+	if (level != LIBBPF_WARN ||
+	    strcmp(format, "libbpf: \n%s\n")) {
+		vprintf(format, args);
+		return 0;
+	}
+
+	log_buf = va_arg(args, char *);
+	if (!log_buf)
+		goto out;
+	if (err_str && strstr(log_buf, err_str) != NULL)
+		found = true;
+out:
+	printf(format, log_buf);
+	return 0;
+}
+
+static void test_invalid_license(void)
+{
+	libbpf_print_fn_t old_print_fn;
+	struct bpf_tcp_nogpl *skel;
+
+	err_str = "struct ops programs must have a GPL compatible license";
+	found = false;
+	old_print_fn = libbpf_set_print(libbpf_debug_print);
+
+	skel = bpf_tcp_nogpl__open_and_load();
+	ASSERT_NULL(skel, "bpf_tcp_nogpl");
+	ASSERT_EQ(found, true, "expected_err_msg");
+
+	bpf_tcp_nogpl__destroy(skel);
+	libbpf_set_print(old_print_fn);
+}
+
 void test_bpf_tcp_ca(void)
 {
 	if (test__start_subtest("dctcp"))
 		test_dctcp();
 	if (test__start_subtest("cubic"))
 		test_cubic();
+	if (test__start_subtest("invalid_license"))
+		test_invalid_license();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
index 36af1c138faf..b62a39315336 100644
--- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c
+++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
@@ -128,6 +128,8 @@ static void test_check_mtu_xdp(__u32 mtu, __u32 ifindex)
 	test_check_mtu_run_xdp(skel, skel->progs.xdp_use_helper, mtu);
 	test_check_mtu_run_xdp(skel, skel->progs.xdp_exceed_mtu, mtu);
 	test_check_mtu_run_xdp(skel, skel->progs.xdp_minus_delta, mtu);
+	test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len, mtu);
+	test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len_exceed, mtu);
 
 cleanup:
 	test_check_mtu__destroy(skel);
@@ -187,6 +189,8 @@ static void test_check_mtu_tc(__u32 mtu, __u32 ifindex)
 	test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu, mtu);
 	test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu_da, mtu);
 	test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu);
+	test_check_mtu_run_tc(skel, skel->progs.tc_input_len, mtu);
+	test_check_mtu_run_tc(skel, skel->progs.tc_input_len_exceed, mtu);
 cleanup:
 	test_check_mtu__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
new file mode 100644
index 000000000000..6c4d42a2386f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <test_progs.h>
+#include <time.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include "fexit_sleep.skel.h"
+
+static int do_sleep(void *skel)
+{
+	struct fexit_sleep *fexit_skel = skel;
+	struct timespec ts1 = { .tv_nsec = 1 };
+	struct timespec ts2 = { .tv_sec = 10 };
+
+	fexit_skel->bss->pid = getpid();
+	(void)syscall(__NR_nanosleep, &ts1, NULL);
+	(void)syscall(__NR_nanosleep, &ts2, NULL);
+	return 0;
+}
+
+#define STACK_SIZE (1024 * 1024)
+static char child_stack[STACK_SIZE];
+
+void test_fexit_sleep(void)
+{
+	struct fexit_sleep *fexit_skel = NULL;
+	int wstatus, duration = 0;
+	pid_t cpid;
+	int err, fexit_cnt;
+
+	fexit_skel = fexit_sleep__open_and_load();
+	if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
+		goto cleanup;
+
+	err = fexit_sleep__attach(fexit_skel);
+	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
+		goto cleanup;
+
+	cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
+	if (CHECK(cpid == -1, "clone", strerror(errno)))
+		goto cleanup;
+
+	/* wait until first sys_nanosleep ends and second sys_nanosleep starts */
+	while (READ_ONCE(fexit_skel->bss->fentry_cnt) != 2);
+	fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt);
+	if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt))
+		goto cleanup;
+
+	/* close progs and detach them. That will trigger two nop5->jmp5 rewrites
+	 * in the trampolines to skip nanosleep_fexit prog.
+	 * The nanosleep_fentry prog will get detached first.
+	 * The nanosleep_fexit prog will get detached second.
+	 * Detaching will trigger freeing of both progs JITed images.
+	 * There will be two dying bpf_tramp_image-s, but only the initial
+	 * bpf_tramp_image (with both _fentry and _fexit progs will be stuck
+	 * waiting for percpu_ref_kill to confirm). The other one
+	 * will be freed quickly.
+	 */
+	close(bpf_program__fd(fexit_skel->progs.nanosleep_fentry));
+	close(bpf_program__fd(fexit_skel->progs.nanosleep_fexit));
+	fexit_sleep__detach(fexit_skel);
+
+	/* kill the thread to unwind sys_nanosleep stack through the trampoline */
+	kill(cpid, 9);
+
+	if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno)))
+		goto cleanup;
+	if (CHECK(WEXITSTATUS(wstatus) != 0, "exitstatus", "failed"))
+		goto cleanup;
+
+	/* The bypassed nanosleep_fexit prog shouldn't have executed.
+	 * Unlike progs the maps were not freed and directly accessible.
+	 */
+	fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt);
+	if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt))
+		goto cleanup;
+
+cleanup:
+	fexit_sleep__destroy(fexit_skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c
new file mode 100644
index 000000000000..2ecd833dcd41
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "X";
+
+void BPF_STRUCT_OPS(nogpltcp_init, struct sock *sk)
+{
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops bpf_nogpltcp = {
+	.init           = (void *)nogpltcp_init,
+	.name           = "bpf_nogpltcp",
+};
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index 31975c96e2c9..3ac0c9afc35a 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -174,6 +174,12 @@ struct struct_in_struct {
 	};
 };
 
+struct struct_in_array {};
+
+struct struct_in_array_typed {};
+
+typedef struct struct_in_array_typed struct_in_array_t[2];
+
 struct struct_with_embedded_stuff {
 	int a;
 	struct {
@@ -203,6 +209,8 @@ struct struct_with_embedded_stuff {
 	} r[5];
 	struct struct_in_struct s[10];
 	int t[11];
+	struct struct_in_array (*u)[2];
+	struct_in_array_t *v;
 };
 
 struct root_struct {
diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c
new file mode 100644
index 000000000000..03a672d76353
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+int pid = 0;
+int fentry_cnt = 0;
+int fexit_cnt = 0;
+
+SEC("fentry/__x64_sys_nanosleep")
+int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs)
+{
+	if ((int)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	fentry_cnt++;
+	return 0;
+}
+
+SEC("fexit/__x64_sys_nanosleep")
+int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret)
+{
+	if ((int)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	fexit_cnt++;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c
index b7787b43f9db..c4a9bae96e75 100644
--- a/tools/testing/selftests/bpf/progs/test_check_mtu.c
+++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c
@@ -105,6 +105,54 @@ int xdp_minus_delta(struct xdp_md *ctx)
 	return retval;
 }
 
+SEC("xdp")
+int xdp_input_len(struct xdp_md *ctx)
+{
+	int retval = XDP_PASS; /* Expected retval on successful test */
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+	__u32 data_len = data_end - data;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input len is L3, like MTU and iph->tot_len.
+	 * Remember XDP data_len is L2.
+	 */
+	__u32 mtu_len = data_len - ETH_HLEN;
+
+	if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+		retval = XDP_ABORTED;
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
+
+SEC("xdp")
+int xdp_input_len_exceed(struct xdp_md *ctx)
+{
+	int retval = XDP_ABORTED; /* Fail */
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+	int err;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input length value is L3 size like MTU.
+	 */
+	__u32 mtu_len = GLOBAL_USER_MTU;
+
+	mtu_len += 1; /* Exceed with 1 */
+
+	err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+	if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+		retval = XDP_PASS ; /* Success in exceeding MTU check */
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
+
 SEC("classifier")
 int tc_use_helper(struct __sk_buff *ctx)
 {
@@ -196,3 +244,47 @@ int tc_minus_delta(struct __sk_buff *ctx)
 	global_bpf_mtu_xdp = mtu_len;
 	return retval;
 }
+
+SEC("classifier")
+int tc_input_len(struct __sk_buff *ctx)
+{
+	int retval = BPF_OK; /* Expected retval on successful test */
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input length value is L3 size.
+	 */
+	__u32 mtu_len = GLOBAL_USER_MTU;
+
+	if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+		retval = BPF_DROP;
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
+
+SEC("classifier")
+int tc_input_len_exceed(struct __sk_buff *ctx)
+{
+	int retval = BPF_DROP; /* Fail */
+	__u32 ifindex = GLOBAL_USER_IFINDEX;
+	int err;
+
+	/* API allow user give length to check as input via mtu_len param,
+	 * resulting MTU value is still output in mtu_len param after call.
+	 *
+	 * Input length value is L3 size like MTU.
+	 */
+	__u32 mtu_len = GLOBAL_USER_MTU;
+
+	mtu_len += 1; /* Exceed with 1 */
+
+	err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+	if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+		retval = BPF_OK; /* Success in exceeding MTU check */
+
+	global_bpf_mtu_xdp = mtu_len;
+	return retval;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 9afe947cfae9..ba6eadfec565 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -508,10 +508,8 @@ int _ip6geneve_get_tunnel(struct __sk_buff *skb)
 	}
 
 	ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
-	if (ret < 0) {
-		ERROR(ret);
-		return TC_ACT_SHOT;
-	}
+	if (ret < 0)
+		gopt.opt_class = 0;
 
 	bpf_trace_printk(fmt, sizeof(fmt),
 			key.tunnel_id, key.remote_ipv4, gopt.opt_class);
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index 57ed67b86074..8a1caf46ffbc 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -261,8 +261,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	/* not actually fully unbounded, but the bound is very high */
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
-	.result_unpriv = REJECT,
 	.errstr = "value -4294967168 makes map_value pointer be out of bounds",
 	.result = REJECT,
 },
@@ -298,9 +296,6 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 3 },
-	/* not actually fully unbounded, but the bound is very high */
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
-	.result_unpriv = REJECT,
 	.errstr = "value -4294967168 makes map_value pointer be out of bounds",
 	.result = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/bounds_deduction.c b/tools/testing/selftests/bpf/verifier/bounds_deduction.c
index 1fd07a4f27ac..91869aea6d64 100644
--- a/tools/testing/selftests/bpf/verifier/bounds_deduction.c
+++ b/tools/testing/selftests/bpf/verifier/bounds_deduction.c
@@ -6,8 +6,9 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 2",
@@ -20,6 +21,8 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
 		BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 1,
 },
@@ -31,20 +34,24 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 4",
 	.insns = {
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 1),
 		BPF_EXIT_INSN(),
 		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
 		BPF_EXIT_INSN(),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+		BPF_ALU64_REG(BPF_SUB, BPF_REG_6, BPF_REG_0),
 		BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R6 has pointer with unsupported alu operation",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -55,8 +62,9 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 6",
@@ -67,8 +75,9 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 7",
@@ -80,8 +89,9 @@
 			    offsetof(struct __sk_buff, mark)),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "dereference of modified ctx ptr",
+	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
@@ -94,8 +104,9 @@
 			    offsetof(struct __sk_buff, mark)),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "dereference of modified ctx ptr",
+	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
@@ -106,8 +117,9 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.errstr = "R0 tried to subtract pointer from scalar",
+	.result = REJECT,
 },
 {
 	"check deducing bounds from const, 10",
@@ -119,6 +131,6 @@
 		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
 		BPF_EXIT_INSN(),
 	},
-	.result = REJECT,
 	.errstr = "math between ctx pointer and register with unbounded min value is not allowed",
+	.result = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c
index 9baca7a75c42..c2aa6f26738b 100644
--- a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c
+++ b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c
@@ -19,7 +19,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -43,7 +42,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -69,7 +67,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R8 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -94,7 +91,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R8 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -141,7 +137,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -210,7 +205,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -260,7 +254,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -287,7 +280,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -313,7 +305,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -342,7 +333,6 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R7 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -372,7 +362,6 @@
 	},
 	.fixup_map_hash_8b = { 4 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
 },
 {
@@ -400,7 +389,5 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	.errstr = "unbounded min value",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
 	.result = REJECT,
-	.result_unpriv = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c
index b117bdd3806d..1f82021429bf 100644
--- a/tools/testing/selftests/bpf/verifier/map_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_ptr.c
@@ -75,6 +75,8 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_16b = { 4 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
 	.result = ACCEPT,
 },
 {
@@ -91,5 +93,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_16b = { 4 },
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R0 has pointer with unsupported alu operation",
 	.result = ACCEPT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index b018ad71e0a8..bd436df5cc32 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -497,7 +497,7 @@
 	.result = ACCEPT,
 },
 {
-	"unpriv: adding of fp",
+	"unpriv: adding of fp, reg",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_MOV64_IMM(BPF_REG_1, 0),
@@ -510,6 +510,19 @@
 	.result = ACCEPT,
 },
 {
+	"unpriv: adding of fp, imm",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0),
+	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
+	BPF_EXIT_INSN(),
+	},
+	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
+	.result_unpriv = REJECT,
+	.result = ACCEPT,
+},
+{
 	"unpriv: cmp of stack pointer",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index ed4e76b24649..e5913fd3b903 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -21,8 +21,6 @@
 	.fixup_map_hash_16b = { 5 },
 	.fixup_map_array_48b = { 8 },
 	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 tried to add from different maps",
 	.retval = 1,
 },
 {
@@ -122,7 +120,7 @@
 	.fixup_map_array_48b = { 1 },
 	.result = ACCEPT,
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R2 tried to add from different pointers or scalars",
+	.errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
 	.retval = 0,
 },
 {
@@ -169,7 +167,7 @@
 	.fixup_map_array_48b = { 1 },
 	.result = ACCEPT,
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R2 tried to add from different maps or paths",
+	.errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
 	.retval = 0,
 },
 {
@@ -517,6 +515,27 @@
 	.retval = 0xabcdef12,
 },
 {
+	"map access: value_ptr += N, value_ptr -= N known scalar",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+	BPF_MOV32_IMM(BPF_REG_1, 0x12345678),
+	BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2),
+	BPF_MOV64_IMM(BPF_REG_1, 2),
+	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 3 },
+	.result = ACCEPT,
+	.retval = 0x12345678,
+},
+{
 	"map access: unknown scalar += value_ptr, 1",
 	.insns = {
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c
index 2f2eeb8a1d86..5aadf84c91c0 100644
--- a/tools/testing/selftests/kvm/hardware_disable_test.c
+++ b/tools/testing/selftests/kvm/hardware_disable_test.c
@@ -108,7 +108,7 @@ static void run_test(uint32_t run)
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 	vm_create_irqchip(vm);
 
-	fprintf(stderr, "%s: [%d] start vcpus\n", __func__, run);
+	pr_debug("%s: [%d] start vcpus\n", __func__, run);
 	for (i = 0; i < VCPU_NUM; ++i) {
 		vm_vcpu_add_default(vm, i, guest_code);
 		payloads[i].vm = vm;
@@ -124,7 +124,7 @@ static void run_test(uint32_t run)
 			check_set_affinity(throw_away, &cpu_set);
 		}
 	}
-	fprintf(stderr, "%s: [%d] all threads launched\n", __func__, run);
+	pr_debug("%s: [%d] all threads launched\n", __func__, run);
 	sem_post(sem);
 	for (i = 0; i < VCPU_NUM; ++i)
 		check_join(threads[i], &b);
@@ -147,16 +147,16 @@ int main(int argc, char **argv)
 		if (pid == 0)
 			run_test(i); /* This function always exits */
 
-		fprintf(stderr, "%s: [%d] waiting semaphore\n", __func__, i);
+		pr_debug("%s: [%d] waiting semaphore\n", __func__, i);
 		sem_wait(sem);
 		r = (rand() % DELAY_US_MAX) + 1;
-		fprintf(stderr, "%s: [%d] waiting %dus\n", __func__, i, r);
+		pr_debug("%s: [%d] waiting %dus\n", __func__, i, r);
 		usleep(r);
 		r = waitpid(pid, &s, WNOHANG);
 		TEST_ASSERT(r != pid,
 			    "%s: [%d] child exited unexpectedly status: [%d]",
 			    __func__, i, s);
-		fprintf(stderr, "%s: [%d] killing child\n", __func__, i);
+		pr_debug("%s: [%d] killing child\n", __func__, i);
 		kill(pid, SIGKILL);
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index ffbc4555c6e2..7f1d2765572c 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -80,19 +80,24 @@ static inline void check_tsc_msr_rdtsc(void)
 	GUEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100);
 }
 
+static inline u64 get_tscpage_ts(struct ms_hyperv_tsc_page *tsc_page)
+{
+	return mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+}
+
 static inline void check_tsc_msr_tsc_page(struct ms_hyperv_tsc_page *tsc_page)
 {
 	u64 r1, r2, t1, t2;
 
 	/* Compare TSC page clocksource with HV_X64_MSR_TIME_REF_COUNT */
-	t1 = mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+	t1 = get_tscpage_ts(tsc_page);
 	r1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
 
 	/* 10 ms tolerance */
 	GUEST_ASSERT(r1 >= t1 && r1 - t1 < 100000);
 	nop_loop();
 
-	t2 = mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+	t2 = get_tscpage_ts(tsc_page);
 	r2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
 	GUEST_ASSERT(r2 >= t1 && r2 - t2 < 100000);
 }
@@ -130,7 +135,11 @@ static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_
 
 	tsc_offset = tsc_page->tsc_offset;
 	/* Call KVM_SET_CLOCK from userspace, check that TSC page was updated */
+
 	GUEST_SYNC(7);
+	/* Sanity check TSC page timestamp, it should be close to 0 */
+	GUEST_ASSERT(get_tscpage_ts(tsc_page) < 100000);
+
 	GUEST_ASSERT(tsc_page->tsc_offset != tsc_offset);
 
 	nop_loop();
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index ce6bea9675c0..eb307ca37bfa 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -657,10 +657,21 @@ test_ecn_decap()
 {
 	# In accordance with INET_ECN_decapsulate()
 	__test_ecn_decap 00 00 0x00
+	__test_ecn_decap 00 01 0x00
+	__test_ecn_decap 00 02 0x00
+	# 00 03 is tested in test_ecn_decap_error()
+	__test_ecn_decap 01 00 0x01
 	__test_ecn_decap 01 01 0x01
-	__test_ecn_decap 02 01 0x02
+	__test_ecn_decap 01 02 0x01
 	__test_ecn_decap 01 03 0x03
+	__test_ecn_decap 02 00 0x02
+	__test_ecn_decap 02 01 0x01
+	__test_ecn_decap 02 02 0x02
 	__test_ecn_decap 02 03 0x03
+	__test_ecn_decap 03 00 0x03
+	__test_ecn_decap 03 01 0x03
+	__test_ecn_decap 03 02 0x03
+	__test_ecn_decap 03 03 0x03
 	test_ecn_decap_error
 }
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 964db9ed544f..ad32240fbfda 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -11,6 +11,7 @@ ksft_skip=4
 timeout=30
 mptcp_connect=""
 capture=0
+do_all_tests=1
 
 TEST_COUNT=0
 
@@ -121,12 +122,6 @@ reset_with_add_addr_timeout()
 		-j DROP
 }
 
-for arg in "$@"; do
-	if [ "$arg" = "-c" ]; then
-		capture=1
-	fi
-done
-
 ip -Version > /dev/null 2>&1
 if [ $? -ne 0 ];then
 	echo "SKIP: Could not run test without ip tool"
@@ -1221,7 +1216,8 @@ usage()
 	echo "  -4 v4mapped_tests"
 	echo "  -b backup_tests"
 	echo "  -p add_addr_ports_tests"
-	echo "  -c syncookies_tests"
+	echo "  -k syncookies_tests"
+	echo "  -c capture pcap files"
 	echo "  -h help"
 }
 
@@ -1235,12 +1231,24 @@ make_file "$cin" "client" 1
 make_file "$sin" "server" 1
 trap cleanup EXIT
 
-if [ -z $1 ]; then
+for arg in "$@"; do
+	# check for "capture" arg before launching tests
+	if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then
+		capture=1
+	fi
+
+	# exception for the capture option, the rest means: a part of the tests
+	if [ "${arg}" != "-c" ]; then
+		do_all_tests=0
+	fi
+done
+
+if [ $do_all_tests -eq 1 ]; then
 	all_tests
 	exit $ret
 fi
 
-while getopts 'fsltra64bpch' opt; do
+while getopts 'fsltra64bpkch' opt; do
 	case $opt in
 		f)
 			subflows_tests
@@ -1272,9 +1280,11 @@ while getopts 'fsltra64bpch' opt; do
 		p)
 			add_addr_ports_tests
 			;;
-		c)
+		k)
 			syncookies_tests
 			;;
+		c)
+			;;
 		h | *)
 			usage
 			;;
diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
index 7b01b7c2ec10..066efd30e294 100644
--- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
+++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
@@ -30,25 +30,25 @@ struct reuse_opts {
 };
 
 struct reuse_opts unreusable_opts[12] = {
-	{0, 0, 0, 0},
-	{0, 0, 0, 1},
-	{0, 0, 1, 0},
-	{0, 0, 1, 1},
-	{0, 1, 0, 0},
-	{0, 1, 0, 1},
-	{0, 1, 1, 0},
-	{0, 1, 1, 1},
-	{1, 0, 0, 0},
-	{1, 0, 0, 1},
-	{1, 0, 1, 0},
-	{1, 0, 1, 1},
+	{{0, 0}, {0, 0}},
+	{{0, 0}, {0, 1}},
+	{{0, 0}, {1, 0}},
+	{{0, 0}, {1, 1}},
+	{{0, 1}, {0, 0}},
+	{{0, 1}, {0, 1}},
+	{{0, 1}, {1, 0}},
+	{{0, 1}, {1, 1}},
+	{{1, 0}, {0, 0}},
+	{{1, 0}, {0, 1}},
+	{{1, 0}, {1, 0}},
+	{{1, 0}, {1, 1}},
 };
 
 struct reuse_opts reusable_opts[4] = {
-	{1, 1, 0, 0},
-	{1, 1, 0, 1},
-	{1, 1, 1, 0},
-	{1, 1, 1, 1},
+	{{1, 1}, {0, 0}},
+	{{1, 1}, {0, 1}},
+	{{1, 1}, {1, 0}},
+	{{1, 1}, {1, 1}},
 };
 
 int bind_port(struct __test_metadata *_metadata, int reuseaddr, int reuseport)
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d42115e4284d..8b0cd421ebd3 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -101,7 +101,7 @@ endef
 ifeq ($(CAN_BUILD_I386),1)
 $(BINARIES_32): CFLAGS += -m32
 $(BINARIES_32): LDLIBS += -lrt -ldl -lm
-$(BINARIES_32): %_32: %.c
+$(BINARIES_32): $(OUTPUT)/%_32: %.c
 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
 $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t))))
 endif
@@ -109,7 +109,7 @@ endif
 ifeq ($(CAN_BUILD_X86_64),1)
 $(BINARIES_64): CFLAGS += -m64
 $(BINARIES_64): LDLIBS += -lrt -ldl
-$(BINARIES_64): %_64: %.c
+$(BINARIES_64): $(OUTPUT)/%_64: %.c
 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
 $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t))))
 endif